{"id":"https://openalex.org/W2079594573","doi":"https://doi.org/10.1145/1458502.1458505","title":"Automatic wrapper induction from hidden-web sources with domain knowledge","display_name":"Automatic wrapper induction from hidden-web sources with domain knowledge","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2079594573","doi":"https://doi.org/10.1145/1458502.1458505","mag":"2079594573"},"language":"en","primary_location":{"id":"doi:10.1145/1458502.1458505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458502.1458505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM workshop on Web information and data management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035414136","display_name":"Pierre Senellart","orcid":"https://orcid.org/0000-0002-7909-5369"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Senellart","raw_affiliation_strings":["INRIA Saclay &amp; TELECOM ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Saclay &amp; TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089089341","display_name":"A. Mittal","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avin Mittal","raw_affiliation_strings":["Indian Institute of Technology, Bombay, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059870247","display_name":"Daniel Muschick","orcid":"https://orcid.org/0000-0001-5945-8874"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Daniel Muschick","raw_affiliation_strings":["Technische Universit\u00e4t Graz, Graz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Graz, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108264210","display_name":"R\u00e9mi Gilleron","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"R\u00e9mi Gilleron","raw_affiliation_strings":["Universit\u00e9 Lille 3 &amp; INRIA Lille, Villeneuve d'Ascq, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Lille 3 &amp; INRIA Lille, Villeneuve d'Ascq, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047374978","display_name":"Marc Tommasi","orcid":"https://orcid.org/0000-0003-2838-4408"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc Tommasi","raw_affiliation_strings":["Universit\u00e9 Lille 3 &amp; INRIA Lille, Villeneuve d'Ascq, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Lille 3 &amp; INRIA Lille, Villeneuve d'Ascq, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.3898,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.99007158,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039321899414062},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7183102369308472},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6851962208747864},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6009401082992554},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.539368748664856},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5231053829193115},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5034641623497009},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46761593222618103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4534114599227905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3308241367340088},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32272714376449585},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2231585681438446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07173684239387512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039321899414062},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7183102369308472},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6851962208747864},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6009401082992554},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.539368748664856},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5231053829193115},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5034641623497009},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46761593222618103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4534114599227905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3308241367340088},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32272714376449585},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2231585681438446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07173684239387512},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1458502.1458505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458502.1458505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.175.8077","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.175.8077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pierre.senellart.com/publications/senellart2008automatic.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W200042785","https://openalex.org/W1494141893","https://openalex.org/W1502166968","https://openalex.org/W1541624846","https://openalex.org/W1553019137","https://openalex.org/W1596067154","https://openalex.org/W1616576116","https://openalex.org/W1691409177","https://openalex.org/W2013970953","https://openalex.org/W2014959658","https://openalex.org/W2020298184","https://openalex.org/W2026080185","https://openalex.org/W2034797903","https://openalex.org/W2098162425","https://openalex.org/W2104086170","https://openalex.org/W2108126629","https://openalex.org/W2118356300","https://openalex.org/W2119088569","https://openalex.org/W2121911355","https://openalex.org/W2123853152","https://openalex.org/W2131006463","https://openalex.org/W2141099517","https://openalex.org/W2143309843","https://openalex.org/W2143607396","https://openalex.org/W2147880316","https://openalex.org/W2150721933","https://openalex.org/W2156515921","https://openalex.org/W2157813460","https://openalex.org/W2158188757","https://openalex.org/W2163767763","https://openalex.org/W2170188121","https://openalex.org/W2301435905","https://openalex.org/W6608051331","https://openalex.org/W6635610519","https://openalex.org/W6685116542","https://openalex.org/W6902931378"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W1583422155","https://openalex.org/W2158321484","https://openalex.org/W3213252596","https://openalex.org/W1649619740","https://openalex.org/W1534006406"],"abstract_inverted_index":{"We":[0,121],"present":[1],"an":[2,76,111],"original":[3],"approach":[4,25],"to":[5,63,107],"the":[6,14,52,66,81,97,118,126,131],"automatic":[7],"induction":[8],"of":[9,13,34,54,65,88,91,130],"wrappers":[10],"for":[11,96],"sources":[12],"hidden":[15],"Web":[16],"that":[17,124],"does":[18],"not":[19],"need":[20],"any":[21],"human":[22],"supervision.":[23],"Our":[24],"only":[26],"needs":[27],"domain":[28,94,119],"knowledge":[29],"expressed":[30],"as":[31],"a":[32,55,86,101],"set":[33],"concept":[35,38],"names":[36],"and":[37,59,68,90,114,128],"instances.":[39],"There":[40],"are":[41,73],"two":[42],"parts":[43],"in":[44,75],"extracting":[45],"valuable":[46],"data":[47],"from":[48],"hidden-Web":[49],"sources:":[50],"understanding":[51,69],"structure":[53],"given":[56],"HTML":[57,77],"form":[58],"relating":[60],"its":[61],"fields":[62],"concepts":[64],"domain,":[67],"how":[70],"resulting":[71],"records":[72],"represented":[74],"result":[78],"page.":[79],"For":[80],"former":[82],"problem,":[83],"we":[84,99],"use":[85,100],"combination":[87],"heuristics":[89],"probing":[92],"with":[93],"instances;":[95],"latter,":[98],"supervised":[102],"machine":[103],"learning":[104],"technique":[105],"adapted":[106],"tree-like":[108],"information":[109],"on":[110],"automatic,":[112],"imperfect,":[113],"imprecise,":[115],"annotation":[116],"using":[117],"knowledge.":[120],"show":[122],"experiments":[123],"demonstrate":[125],"validity":[127],"potential":[129],"approach.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
